Update app.py

app.py

@@ -1,10 +1,6 @@
 import gradio as gr
 
-def greet(name):
-    return "Hello " + name + "!!"
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-demo.launch()
 
 # Load vision capability to support image display
 ##pip install datasets
@@ -26,8 +22,61 @@ print(df.head(20))
 
 # Use the sample command 
 selected_image = df.sample(n=1)
+
+
+# Get url for image
+def parse_url(df):
+    for index, row in df.iterrows():
+        parsed = urlparse(str(row)).query # <- Notice the change here
+        parsed = parse_qs(parsed)
+        for k, v in parsed.items(): #use items() in Python3 and iteritems() in Python2
+            df.loc[index, k.strip()] = v[0].strip().lower()
+    return df
+
+
+image_url = parse_url(df['image'])
+
+
+
+
 print (selected_image)
 
+
+
+def greet(name):
+    return "Hello " + name + "!!"
+
+demo = gr.Interface(fn=greet, inputs="text", outputs="text")
+demo.launch()
+
+import requests
+from PIL import Image
+from transformers import BlipProcessor, BlipForConditionalGeneration
+
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
+
+
+##img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' 
+#Select image
+
+raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
+
+# conditional image captioning
+text = "a photography of"
+inputs = processor(raw_image, text, return_tensors="pt")
+
+out = model.generate(**inputs)
+print(processor.decode(out[0], skip_special_tokens=True))
+
+# unconditional image captioning
+inputs = processor(raw_image, return_tensors="pt")
+
+out = model.generate(**inputs)
+print(processor.decode(out[0], skip_special_tokens=True))
+
+
+
 # Get image database
 ##curl -X GET \
 ##     "https://datasets-server.huggingface.co/first-rows?dataset=merve%2Fcoco&config=default&split=validation"